[PATCH] Make XDF_NEED_MINIMAL default in blame.

From: Michael Andreen <harv@ruin.nu>
Date: Mar 16, 2014, 10:43 UTC
Message-ID: <154997837.FlSR2gFiUN@river>

Currently git blame has a big problem finding copies and moves when you split up a big file into smaller ones. One example in the git repository is 2cf565c, which split the documentation into smaller files.

In 582aa00 XDF_NEED_MINIMAL was removed as the default for performance reasons, mainly for diff and rebase, but blame was also changed.

In 059a500 the problem with blame was noticed and the flag --minimal was introduced. However this flag is not documented and it is not possible to set when using "git gui blame".

Setting XDF_NEED_MINIMAL as default has a small performance impact when you run on a file with few modifications. However, if you run it on a file with a bigger number of modifications, the performance impact is small enough to not be noticable.

((2cf565c...))$ time PAGER=cat git blame -C -M
    Documentation/git-ls-files.txt > /dev/null

real 0m0.003s user 0m0.002s sys 0m0.000s

((2cf565c...))$ time PAGER=cat git blame --minimal -C -M
    Documentation/git-ls-files.txt > /dev/null

real 0m0.010s user 0m0.009s sys 0m0.000s

((2cf565c...))$ time PAGER=cat git blame -C -C -C -M
    Documentation/git-ls-files.txt > /dev/null

real 0m0.010s user 0m0.010s sys 0m0.000s

((2cf565c...))$ time PAGER=cat git blame --minimal -C -C -C -M
    Documentation/git-ls-files.txt > /dev/null

real 0m0.028s user 0m0.027s sys 0m0.000s

(master)$ time PAGER=cat git blame -C -C -C -M
    Documentation/git-ls-files.txt > /dev/null

real 0m2.338s user 0m2.283s sys 0m0.056s

(master)$ time PAGER=cat git blame --minimal -C -C -C -M
    Documentation/git-ls-files.txt > /dev/null

real 0m2.355s user 0m2.285s sys 0m0.069s

(master)$ time PAGER=cat git blame -C -M cache.h > /dev/null

real 0m1.755s user 0m1.730s sys 0m0.024s

(master)$ time PAGER=cat git blame --minimal -C -M cache.h > /dev/null

real 0m1.785s user 0m1.770s sys 0m0.014s

(master)$ time PAGER=cat git blame -C -C -C -M cache.h > /dev/null

real 0m31.515s user 0m30.810s sys 0m0.684s

(master)$ time PAGER=cat git blame --minimal -C -C -C -M cache.h > /dev/null

real 0m31.504s user 0m30.885s sys 0m0.598s

Signed-off-by: Michael Andreen <harv@ruin.nu>
---
Additional measurements attached, the variation is fairly small.

The --minimal flag is still there, but didn't want to break scripts depending on it.

 builtin/blame.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/builtin/blame.c b/builtin/blame.c
index e5b5d71..0e7ebd0 100644
--- a/builtin/blame.c
+++ b/builtin/blame.c
@@ -42,7 +42,7 @@ static int show_root;
 static int reverse;
 static int blank_boundary;
 static int incremental;
-static int xdl_opts;
+static int xdl_opts = XDF_NEED_MINIMAL;
 static int abbrev = -1;
 static int no_whole_file_rename;

-- 
1.8.3.2



(master)$ time PAGER=cat git blame -C -M cache.h > /dev/null

real	0m1.767s
user	0m1.747s
sys	0m0.018s
(master)$ time PAGER=cat git blame -C -M cache.h > /dev/null

real	0m1.755s
user	0m1.730s
sys	0m0.024s
(master)$ time PAGER=cat git blame -C -M cache.h > /dev/null

real	0m1.784s
user	0m1.757s
sys	0m0.025s
(master)$ time PAGER=cat git blame --minimal -C -M cache.h > /dev/null

real	0m1.813s
user	0m1.797s
sys	0m0.014s
(master)$ time PAGER=cat git blame --minimal -C -M cache.h > /dev/null

real	0m1.790s
user	0m1.770s
sys	0m0.018s
(master)$ time PAGER=cat git blame --minimal -C -M cache.h > /dev/null

real	0m1.785s
user	0m1.770s
sys	0m0.014s
(master)$ time PAGER=cat git blame --minimal -C -M cache.h > /dev/null

real	0m1.794s
user	0m1.770s
sys	0m0.022s
(master)$ time PAGER=cat git blame -C -C -C -M cache.h > /dev/null

real	0m31.515s
user	0m30.810s
sys	0m0.684s
(master)$ time PAGER=cat git blame -C -C -C -M cache.h > /dev/null

real	0m31.594s
user	0m30.879s
sys	0m0.695s
(master)$ time PAGER=cat git blame --minimal -C -C -C -M cache.h > /dev/null

real	0m31.666s
user	0m31.054s
sys	0m0.591s
(master)$ time PAGER=cat git blame --minimal -C -C -C -M cache.h > /dev/null

real	0m31.504s
user	0m30.885s
sys	0m0.598s

(master)$ time PAGER=cat git blame -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m2.355s
user	0m2.319s
sys	0m0.035s
(master)$ time PAGER=cat git blame -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m2.352s
user	0m2.292s
sys	0m0.059s
(master)$ time PAGER=cat git blame -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m2.354s
user	0m2.312s
sys	0m0.040s
(master)$ time PAGER=cat git blame -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m2.338s
user	0m2.283s
sys	0m0.056s
(master)$ time PAGER=cat git blame --minimal -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m2.376s
user	0m2.302s
sys	0m0.071s
(master)$ time PAGER=cat git blame --minimal -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m2.362s
user	0m2.312s
sys	0m0.049s
(master)$ time PAGER=cat git blame --minimal -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m2.360s
user	0m2.301s
sys	0m0.057s
(master)$ time PAGER=cat git blame --minimal -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m2.355s
user	0m2.285s
sys	0m0.069s


---------------------------------------------------

((2cf565c...))$ time PAGER=cat git blame -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.003s
user	0m0.002s
sys	0m0.000s
((2cf565c...))$ time PAGER=cat git blame -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.003s
user	0m0.003s
sys	0m0.000s
((2cf565c...))$ time PAGER=cat git blame -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.004s
user	0m0.003s
sys	0m0.001s
((2cf565c...))$ time PAGER=cat git blame -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.004s
user	0m0.003s
sys	0m0.001s
((2cf565c...))$ time PAGER=cat git blame -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.003s
user	0m0.002s
sys	0m0.001s
((2cf565c...))$ time PAGER=cat git blame --minimal -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.010s
user	0m0.009s
sys	0m0.000s
((2cf565c...))$ time PAGER=cat git blame --minimal -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.011s
user	0m0.010s
sys	0m0.001s
((2cf565c...))$ time PAGER=cat git blame --minimal -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.012s
user	0m0.012s
sys	0m0.000s
((2cf565c...))$ time PAGER=cat git blame --minimal -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.011s
user	0m0.011s
sys	0m0.000s
((2cf565c...))$ time PAGER=cat git blame -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.008s
user	0m0.007s
sys	0m0.002s
((2cf565c...))$ time PAGER=cat git blame -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.011s
user	0m0.011s
sys	0m0.000s
((2cf565c...))$ time PAGER=cat git blame -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.010s
user	0m0.010s
sys	0m0.000s
((2cf565c...))$ time PAGER=cat git blame -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.010s
user	0m0.009s
sys	0m0.000s
((2cf565c...))$ time PAGER=cat git blame --minimal -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.028s
user	0m0.024s
sys	0m0.003s
((2cf565c...))$ time PAGER=cat git blame --minimal -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.032s
user	0m0.029s
sys	0m0.002s
((2cf565c...))$ time PAGER=cat git blame --minimal -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.027s
user	0m0.025s
sys	0m0.001s
((2cf565c...))$ time PAGER=cat git blame --minimal -C -C -C -M Documentation/git-ls-files.txt > /dev/null

real	0m0.028s
user	0m0.027s
sys	0m0.000s